Text-to-Image Generation on MS-COCO 30k (val)
4.31FIDl-DeTok
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| l-DeTokTokenizer=l-DeTok, Base Generative Model=SiT-B, CFG scale=best2025.07 | 4.31 | — | 24.61 | |
| l-DeTokTokenizer=l-DeTok, Base Generative Model=MAR-B, CFG scale=best2025.07 | 4.97 | — | 24.82 | |
| MAR-VAETokenizer=MAR-VAE, Base Generative Model=SiT-B, CFG scale=best2025.07 | 5.74 | — | 23.5 | |
| VA-VAETokenizer=VA-VAE, Base Generative Model=SiT-B, CFG scale=best2025.07 | 5.83 | — | 25.07 | |
| SD-VAETokenizer=SD-VAE, Base Generative Model=SiT-B, CFG scale=best2025.07 | 6.63 | — | 24 | |
| Stable Diffusion v1.5Guidance Scale=2, Prompt Type=Textual, Image Size=256x256, Diffusion Steps=1002023.05 | 9.74 | 0.3 | — | |
| MULTIFUSIONGuidance Scale=4, Prompt Type=Textual, Image Size=256x256, Diffusion Steps=1002023.05 | 9.9 | 0.29 | — | |
| Stable Diffusion v1.5Guidance Scale=4, Prompt Type=Textual, Image Size=256x256, Diffusion Steps=1002023.05 | 10.19 | 0.31 | — | |
| Efficient UNet + ClockworkResolution=256x256, Sampling steps=8, Scheduler=DPM++, TFLOPS=5.92023.12 | 11.14 | 0.29 | — | |
| MULTIFUSIONGuidance Scale=6, Prompt Type=Textual, Image Size=256x256, Diffusion Steps=1002023.05 | 12.15 | 0.29 | — | |
| MULTIFUSIONGuidance Scale=2, Prompt Type=Textual, Image Size=256x256, Diffusion Steps=1002023.05 | 12.21 | 0.28 | — | |
| SD UNet + ClockworkResolution=256x256, Sampling steps=8, Scheduler=DPM++, TFLOPS=7.32023.12 | 12.27 | 0.291 | — | |
| Efficient UNetResolution=256x256, Sampling steps=8, Scheduler=DPM++, TFLOPS=9.52023.12 | 12.33 | 0.296 | — | |
| Distilled Efficient UNet + ClockworkResolution=256x256, Sampling steps=8, Scheduler=DPM++, TFLOPS=2.92023.12 | 12.37 | 0.291 | — | |
| MAR-VAETokenizer=MAR-VAE, Base Generative Model=MAR-B, CFG scale=best2025.07 | 12.49 | — | 22.07 | |
| Stable Diffusion v1.5Guidance Scale=6, Prompt Type=Textual, Image Size=256x256, Diffusion Steps=1002023.05 | 12.73 | 0.31 | — | |
| SD UNetResolution=256x256, Sampling steps=8, Scheduler=DPM++, TFLOPS=10.82023.12 | 12.77 | 0.296 | — | |
| DUObeta=10002024.07 | 13.37 | 0.3078 | — | |
| SDv1.5 (Teacher)Steps=50, Latency=2.59s, Guidance scale=8, Batch size=12023.11 | 13.45 | 0.322 | — | |
| SD (1.4v)version=1.4v2024.07 | 13.52 | 0.3095 | — | |
| SPM2024.07 | 13.53 | 0.3093 | — | |
| Distilled Efficient UNetResolution=256x256, Sampling steps=8, Scheduler=DPM++, TFLOPS=4.72023.12 | 13.92 | 0.292 | — | |
| SnapFusionResolution=256x256, Sampling steps=8, Scheduler=DPM++, TFLOPS=42023.12 | 14 | 0.3 | — | |
| UCE2024.07 | 14.04 | 0.3074 | — | |
| MULTIFUSIONGuidance Scale=8, Prompt Type=Textual, Image Size=256x256, Diffusion Steps=1002023.05 | 14.19 | 0.3 | — | |
| Stable Diffusion v1.5Guidance Scale=8, Prompt Type=Textual, Image Size=256x256, Diffusion Steps=1002023.05 | 14.62 | 0.31 | — | |
| DMDSteps=1, Latency=0.09s, Guidance scale=8, Batch size=12023.11 | 14.93 | 0.32 | — | |
| ESD2024.07 | 16.87 | 0.2944 | — | |
| BK-SDM-BaseResolution=256x256, Sampling steps=8, Scheduler=DPM++, TFLOPS=8.42023.12 | 17.23 | 0.287 | — | |
| BK-SDM-SmallResolution=256x256, Sampling steps=8, Scheduler=DPM++, TFLOPS=8.22023.12 | 17.72 | 0.268 | — | |
| DUObeta=5002024.07 | 18.28 | 0.3018 | — | |
| BK-SDM-TinyResolution=256x256, Sampling steps=8, Scheduler=DPM++, TFLOPS=7.82023.12 | 18.64 | 0.265 | — | |
| SD-VAETokenizer=SD-VAE, Base Generative Model=MAR-B, CFG scale=best2025.07 | 19.75 | — | 22.86 | |
| InstaFlowResolution=256x256, Sampling steps=1, Scheduler=None, TFLOPS=0.82023.12 | 20 | — | — | |
| DPM++Steps=4, Latency=0.26s, Guidance scale=8, Batch size=12023.11 | 22.44 | 0.309 | — | |
| UniPCSteps=4, Latency=0.26s, Guidance scale=8, Batch size=12023.11 | 23.3 | 0.308 | — | |
| LCM-LoRASteps=4, Latency=0.19s, Guidance scale=7.5, Batch size=12023.11 | 23.62 | 0.297 | — | |
| LCM-LoRASteps=2, Latency=0.12s, Guidance scale=7.5, Batch size=12023.11 | 24.28 | 0.294 | — | |
| Stable Diffusion v1.5Guidance Scale=1, Prompt Type=Textual, Image Size=256x256, Diffusion Steps=1002023.05 | 26.09 | 0.27 | — | |
| MULTIFUSIONGuidance Scale=1, Prompt Type=Textual, Image Size=256x256, Diffusion Steps=1002023.05 | 32.81 | 0.25 | — | |
| VA-VAETokenizer=VA-VAE, Base Generative Model=MAR-B, CFG scale=best2025.07 | 34.64 | — | 21.98 | |
| LCM-LoRASteps=1, Latency=0.09s, Guidance scale=7.5, Batch size=12023.11 | 77.9 | 0.238 | — | |
| DPM-Solver++(2M)NFE=8, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 28.5 | |
| DPM-Solver++(2M)NFE=12, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 28.65 | |
| DPM-Solver++(2M)NFE=16, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 29.65 | |
| DPM-Solver++(2M)NFE=20, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 30.02 | |
| DyWeightNFE=8, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 28.56 | |
| DyWeightNFE=12, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 29.81 | |
| DyWeightNFE=16, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 30.17 | |
| DyWeightNFE=20, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 30.05 | |
| iPNDM(2M)NFE=8, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 28.33 | |
| iPNDM(2M)NFE=12, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 29.79 | |
| iPNDM(2M)NFE=16, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 30.15 | |
| iPNDM(2M)NFE=20, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 30.3 | |
| UniPC(2M)NFE=8, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 26.44 | |
| UniPC(2M)NFE=12, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 29.05 | |
| UniPC(2M)NFE=16, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 29.79 | |
| UniPC(2M)NFE=20, Base Model=Stable-Diffusion-v1.5, CFG (Classifier-Free Guidance)=True2026.03 | — | — | 30.08 |